From d4e5dc44e48583596ed79cc28468920408f0afa6 Mon Sep 17 00:00:00 2001
From: Dmitry Grigoryev <dmitry@dmitryg.name>
Date: Mon, 10 Jun 2019 21:06:46 +0300
Subject: [PATCH] [tvrain] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/tvrain.py     | 51 ++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 youtube_dl/extractor/tvrain.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index eb5efd1e8..e0d4046c0 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1234,6 +1234,7 @@ from .tvplay import (
     TVPlayHomeIE,
 )
 from .tvplayer import TVPlayerIE
+from .tvrain import TVRainIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
diff --git a/youtube_dl/extractor/tvrain.py b/youtube_dl/extractor/tvrain.py
new file mode 100644
index 000000000..5d9d74d66
--- /dev/null
+++ b/youtube_dl/extractor/tvrain.py
@@ -0,0 +1,51 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class TVRainIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tvrain\.ru.*/(?P<id>[a-z_]+-\d+)/?'
+    _TESTS = [{
+        'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
+        'info_dict': {
+            'id': '582306',
+            'ext': 'mp4',
+            'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
+            'duration': 3382,
+        },
+    }, {
+        'url': 'https://tvrain.ru/teleshow/ted_dod/mozhete_li_vy_reshit_golovolomku_so_shkafchikami-432600/',
+        'info_dict': {
+            'id': '738482',
+            'ext': 'mp4',
+            'title': ' Можете ли вы решить головоломку со шкафчиками? ',
+            'duration': 237,
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        meta = self._search_regex(
+            r'(?s)window\.TVRAIN\.app\s*=\s*({.+?})[\s\/\*\]>]+<\/script>',
+            webpage, 'meta', default=None)
+
+        if meta:
+            article = json.loads(meta)['article']
+            eagle_id = str(article['eagle_id'])
+            return {
+                '_type': 'url',
+                'id': eagle_id,
+                'ie_key': 'EaglePlatform',
+                'url': smuggle_url(
+                    'eagleplatform:tvrainru.media.eagleplatform.com:%s' % eagle_id,
+                    {'referrer': url}),
+            }
+
+        return self.url_result(url, ie='Generic')